biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[ROCm] Enable fused_silu_mul_block_quant on ROCm (#38817)

Browse Source 
Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
This commit is contained in:
Gregory Shtrasberg
2026-04-08 11:23:32 -05:00
committed by GitHub
parent d74a306c4b
commit 56c976c1b5
7 changed files with 28 additions and 29 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
csrc/quantization/fused_kernels/quant_conversions.cuh
View File

@@ -6,7 +6,7 @@
#include "libtorch_stable/quantization/vectorization.cuh"
// TODO(luka/varun):refactor common.cuh to use this file instead
#include "quantization/w8a8/fp8/common.cuh"
#include "../w8a8/fp8/common.cuh"
namespace vllm {